Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to evaluation and assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    verbs ending in ing, ed, ence, ize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "..\..\
    -0.71
     Италијани
    -0.68
    最快更新
    -0.66
    niająca
    -0.64
    Personendaten
    -0.63
    ningens
    -0.59
     "..\..\..\
    -0.59
    MLLoader
    -0.57
    ahuje
    -0.57
    dafx
    -0.56
    POSITIVE LOGITS
     متعلقه
    0.74
     通販
    0.72
    árol
    0.66
    存于互联网档案馆
    0.63
    ingly
    0.63
     derni
    0.62
     تانيه
    0.61
    ing
    0.61
     anvä
    0.59
    ieszcz
    0.59
    Act Density 0.128%

    No Known Activations